arXiv subjects

Yuanliang Sun

Publications and source records attributed to Yuanliang Sun.

4 recordsLinked to original sources

arXiv2026

Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

Graph-based Retrieval-Augmented Generation (GraphRAG) has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches are constrained by their reliance on high-quality knowledge graphs: manually built ones are not scalable, while automatically extracted ones are limited by the performance of LLM extractors, especially when using smaller, local-deployed models. To address this, we introduce Think-on-Graph 3.0 (ToG-3), a novel framework featuring a Multi-Agent Context Evolution and Retrieval (MACER) mechanism. Its core contribution is the dynamic construction and iterative refinement of a Chunk-Triplets-Community heterogeneous graph index, powered by a Dual-Evolution process that adaptively evolves both the query and the retrieved sub-graph during reasoning. ToG-3 dynamically builds a targeted graph index tailored to the query, enabling precise evidence retrieval and reasoning even with lightweight LLMs. Extensive experiments demonstrate that ToG-3 outperforms compared baselines on both deep and broad reasoning benchmarks, and ablation studies confirm the efficacy of the components of MACER framework. The source code are available in https://github.com/DataArcTech/ToG-3.

cs.CL↗

arXiv2025

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: shallow retrieval that fails to surface all critical evidence, and inefficient utilization of pre-constructed structural graph data, which hinders effective reasoning from complex queries. To address these challenges, we propose \textsc{GraphSearch}, a novel agentic deep searching workflow with dual-channel retrieval for GraphRAG. \textsc{GraphSearch} organizes the retrieval process into a modular framework comprising six modules, enabling multi-turn interactions and iterative reasoning. Furthermore, \textsc{GraphSearch} adopts a dual-channel retrieval strategy that issues semantic queries over chunk-based text data and relational queries over structural graph data, enabling comprehensive utilization of both modalities and their complementary strengths. Experimental results across six multi-hop RAG benchmarks demonstrate that \textsc{GraphSearch} consistently improves answer accuracy and generation quality over the traditional strategy, confirming \textsc{GraphSearch} as a promising direction for advancing graph retrieval-augmented generation.

cs.CL↗

arXiv2017

A Privacy-preserving Community-based P2P OSNs Using Broadcast Encryption Supporting Recommendation Mechanism

Online Social Networks (OSNs) have become one of the most important activities on the Internet, such as Facebook and Google+. However, security and privacy have become major concerns in existing C/S based OSNs. In this paper, we propose a novel scheme called a Privacy-preserving Community-based P2P OSNs Using Broadcast Encryption Supporting Recommendation Mechanism (PCBE) that supports cross-platform availability in stringent privacy requirements. For the first time, we introduce recommendation mechanism into a privacy-preserving P2P based OSNs, in which we firstly employ the Open Directory Project to generate user interest model. We firstly introduce broadcast encryption into P2P community-based social networks together with reputation mechanism to decrease the system overhead. We formulate the security requirements and design goals for privacy- preserving P2P based OSNs supporting recommendation mechanism. The RESTful web-services help to ensure cross-platform availability and transmission security. As a result, thorough security analysis and performance evaluation on experiments demonstrate that the PCBE scheme indeed accords with our proposed design goals.

cs.CR↗

arXiv2017

LRSE: A Lightweight Efficient Searchable Encryption Scheme using Local and Global Representations

Cloud computing is emerging as a revolutionary computing paradigm, while security and privacy become major concerns in the cloud scenario. For which Searchable Encryption (SE) technology is proposed to support efficient retrieval of encrypted data. However, the absence of lightweight ranked search with higher search quality in a harsh adversary model is still a typical shortage in existing SE schemes. In this paper, we propose a novel SE scheme called LRSE which firstly integrates machine learning methods into the framework of SE and combines local and global representations of encrypted cloud data to achieve the above design goals. In LRSE, we employ an improved secure kNN scheme to guarantee sufficient privacy protection. Our detailed security analysis shows that LRSE satisfies our formulated privacy requirements. Extensive experiments performed on benchmark datasets demonstrate that LRSE indeed achieves state-of-the-art search quality with lowest system cost.

cs.IR↗